README.md

---
license: apache-2.0
base_model:
- deepseek-ai/DeepSeek-V3
tags:
- deepseek_v3
- bf16
- Safetensors
- custom_code
- Pruned
---

# huihui-ai/DeepSeek-V3-Pruned-Coder-411B




This is a pruned version of the [deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3), 
reduced from 256 experts to 160 experts. The pruned model is mainly used for [code](https://huggingface.co/huihui-ai/DeepSeek-V3-Pruned-Coder-411B/blob/main/coding_problems.py) generation.


This is a test validation to see if we can prune the model according to professional requirements and still maintain acceptable performance. 
The model size has been reduced by about 1/3, and no distortion has occurred.

This allows the model to be pruned according to one's needs.

This pruned model has a total parameter is equivalent to 441B.

We will also try to prune [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1).

## Use with ollama

You can use [huihui_ai/deepseek-v3-pruned](https://ollama.com/huihui_ai/deepseek-v3-pruned) directly
```
ollama run huihui_ai/deepseek-v3-pruned
```


## Use with transformers

```
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch

# Load the model and tokenizer
NEW_MODEL_ID = "huihui-ai/DeepSeek-V3-Pruned-Coder-411B"
quant_config_4 = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=True,
    llm_int8_enable_fp32_cpu_offload=True,
)

model = AutoModelForCausalLM.from_pretrained(
    NEW_MODEL_ID, 
    device_map="auto", 
    trust_remote_code=True,
    quantization_config=quant_config_4,
    torch_dtype=torch.bfloat16
)
tokenizer = AutoTokenizer.from_pretrained(NEW_MODEL_ID, trust_remote_code=True)
if tokenizer.pad_token is None:
    tokenizer.pad_token = tokenizer.eos_token

tokenizer.pad_token_id = tokenizer.eos_token_id

# Initialize conversation context
initial_messages = [
    {"role": "system", "content": "You are a helpful assistant."}
]
messages = initial_messages.copy()  # Copy the initial conversation context

# Enter conversation loop
while True:
    # Get user input
    user_input = input("User: ").strip()  # Strip leading and trailing spaces

    # If the user types '/exit', end the conversation
    if user_input.lower() == "/exit":
        print("Exiting chat.")
        break

    # If the user types '/clean', reset the conversation context
    if user_input.lower() == "/clear":
        messages = initial_messages.copy()  # Reset conversation context
        print("Chat history cleared. Starting a new conversation.")
        continue

    # If input is empty, prompt the user and continue
    if not user_input:
        print("Input cannot be empty. Please enter something.")
        continue

    # Add user input to the conversation
    messages.append({"role": "user", "content": user_input})

    tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)
    response_token_ids = model.generate(tokenized_message['input_ids'].to("cuda:0"), use_cache=False, pad_token_id=tokenizer.pad_token_id, max_new_tokens=8192)
    generated_tokens =response_token_ids[:, len(tokenized_message['input_ids'][0]):]
    response = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]

    # Add the model's response to the conversation
    messages.append({"role": "assistant", "content": response})

    # Print the model's response
    print(f"Response: {response}")
```

### Donation

If you like it, please click 'like' and follow us for more updates.  
You can follow [x.com/support_huihui](https://x.com/support_huihui) to get the latest model information from huihui.ai.

##### Your donation helps us continue our further development and improvement, a cup of coffee can do it.
- bitcoin:
```
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
```